← All headings
AI models & inference
995 listings from 505 providers, 778 answering · counted
Filed by addrbook from the words in each listing, so a heading says what a listing claims to be for.
Showing 301–325, one row per provider, those answering first · names and descriptions as their source publishes them
- Local AI MCPio.github.TMHSDigital/local-ai-mcp · tmhsdigital.github.ioRun, fit, and route work to local LLMs (Ollama, LM Studio, llama.cpp, MLX, vLLM, and more).Livechecked Evidence 1/3WebsiteMCP Registry
- Feedough AI Prompt Generatorcom.feedough.www/prompt-generator · www.feedough.comTurn rough ideas into structured prompts for ChatGPT, Claude, Gemini, image and video AI.Live, sign-in requiredchecked Evidence 1/3MCPWebsiteMCP Registry
- Xcelsior GPU Cloudio.github.aabiro/xcelsior · mcp.xcelsior.caRent GPUs, launch spot instances and run serverless inference on the Xcelsior marketplace.Live, sign-in requiredchecked Evidence 1/3MCPWebsiteMCP Registry
- Timbreio.github.alejandrosml/timbre · alejandrosml.github.ioApple Mail on macOS for all LLMs (Claude, ChatGPT, Gemini, Mistral): local, safe, and undoable.Livechecked Evidence 1/3WebsiteMCP Registry
- AiGanak LLM Costio.github.AiGanak/llm-cost · aiganak.comLLM API prices, cost estimates, model comparisons and language token tax for GPT, Claude and Gemini.Livechecked Evidence 1/3WebsiteMCP Registry
- Prompt Optimizerio.github.nivlewd1/mcp-prompt-optimizer · promptoptimizer.xyzOptimize prompts and generate agent SOPs and skill packages with the Prompt Optimizer cloud API.Livechecked Evidence 1/3WebsiteMCP Registry
- CryptoDataAPI on RealtimeAPIapi.realtimeapi.aiCryptoDataAPI: Get Quant Coin. Full per-coin probability object with explain block (Pro). Everything /quant/market provides, conditioned on the whole-market regime (the coin's transition matrix is the market-posterior-weighted mixture — inspect `explain.transition_mixture_weights`). `recent_regimes` carries the last ~48 inference rows for sparkline rendering. Coins with under 60 days of history return the object flagged `insufficient_history` rather than 404.Livechecked Evidence 1/4x402x402 Bazaar0 payers
- critio.github.crit-labs/crit · crit-hub.devBuild, evaluate and serve a bespoke LLM inference engine for your own GPU with crit's commands.Livechecked Evidence 1/3WebsiteMCP Registry
- Driftlineio.github.AI-Driftline/driftline · aidriftline.comRetirement dates and replacements for OpenAI, Anthropic, Google and 5 more, plus Bedrock and Azure.Livechecked Evidence 1/3WebsiteMCP Registry
- StatsPAIio.github.brycewang-stanford/statspai · brycewang-stanford.github.ioEconometrics and causal inference (DiD, IV, RD, synthetic control, DML) with Stata/R parity gradesLivechecked Evidence 1/3WebsiteMCP Registry
- Gridlineio.github.GridlineGPU/mcp · gridlinegpu.comFine-tune, evaluate and batch open models through Gridline's OpenAI-compatible API.Livechecked Evidence 1/3WebsiteMCP Registry
- querying.aiio.github.OPACTOR-DEV/querying · mcp.querying.aiAI engine answers with sources, prompt research and GEO monitors for ChatGPT, Gemini, Perplexity.Live, sign-in requiredchecked Evidence 1/3MCPWebsiteMCP Registry
- AI API Pricesio.github.Liutasil501/ai-api-prices · aiselect.onlineDaily AI API list prices across 50+ providers: LLM, image, video, speech, search and embeddings.Livechecked Evidence 1/3WebsiteMCP Registry
- SOMA AI Emission Factors (SAEF)io.github.guillermollopis/saef · somaai.earthEstimate carbon, energy and water of AI inference by model class and cloud region (SAEF).Livechecked Evidence 1/3WebsiteMCP Registry
- www.omenz.org/api/tollbooth/v1/secret-scanwww.omenz.orgSecret-Leak Preflight: before a handoff, prompt or payload leaves your boundary, scan it for API keys (Anthropic, OpenAI, AWS, GitHub, Stripe, Slack, Google...), PEM keys, wallet private keys, recovery phrases, DB passwords, JWTs and card numbers. CLEAN / REVIEW / BLOCK with JSON path + offset and redacted previews. Scanned in memory, never stored or logged. By OMENZ.Livechecked Evidence 1/4x402x402 Bazaar
- SpeechWeaveio.github.speechweave/mcp · speechweave.comTranscribe local files and URLs with SpeechWeave's OpenAI-compatible Speech-to-Text API.Livechecked Evidence 1/3WebsiteMCP Registry
- GenPark Jinja-Like Prompt Template Rendererio.github.alphaparkinc/genpark-jinja-like-prompt-template-renderer-skill · genpark.aiSafe zero-dependency Jinja-like prompt template parser and renderer supporting for-loops, if-conditiLivechecked Evidence 0/3WebsiteMCP Registry1 more from genpark.ai
- MedXpert 图书馆连接器(通用版)io.github.zhaoxinghua09-cell/medxpert-library-connector · medxpert.cnLocal RAG MCP server for your own .md knowledge base: BM25 + local Ollama, offline, zero egress.Livechecked Evidence 0/3WebsiteMCP Registry
- io.github.houtini-ai/lmhoutini.comConnect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.Livechecked Evidence 0/3WebsiteMCP Registry
- Eclipse Promptsealio.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/eclipse-promptseal-mcp · eclipsebazaar.comPrompt seal chain + Herald approval binding + incident traceability over fixture prompts only.Livechecked Evidence 0/3WebsiteMCP Registry
- io.github.adamgraymon/ai-inference-proof-escrow-auditorown-adam.onrender.comERC-8183 Proof-of-Inference, Anti-Model-Downgrade & Token Billing Escrow on Base.Livechecked Evidence 0/3MCPMCP Registry
- money-reactor.makar52nn2016.workers.dev/api/ai-chatmoney-reactor.makar52nn2016.workers.devLLM chat completion in ONE call (Llama 3.1 8B via Cloudflare Workers AI): POST {messages:[{role,content}]} or {prompt:'...'} — per-call AI inference, zero signup, zero API keysLivechecked Contradictedx402x402 Bazaar4 payers
- turboshop.ai/api/v1/products/prod-hnsw-vector-indexer/buyturboshop.aiHigh-speed vector computation microservice to compute dot products, cosine similarities, and ranking for 1536-d float32 embeddings.Livechecked Contradictedx402x402 Bazaar1 payer1 more from turboshop.ai
- AgentRXIagentrxi.comOpenAI-compatible chat completions on AI Singapore SEA-LION v4 27B, tuned for Southeast Asian languages (Indonesian, Thai, Vietnamese, Filipino, Malay and more). Set your OpenAI SDK base URL to https://agentrxi.com/v1/sea-lion and pay per token with x402 instead of an API key: $1.053 per million input and $1.665 per million output tokens, minimum $0.002 a call, at most $0.0390. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same requestLivechecked Contradictedx402x402 Bazaar1 payer
- wafermap.xyz/v1/gpt-oss-120bwafermap.xyzGPT-OSS 120B — OpenAI's open-weight 120B. Reasoning at a low price.Livechecked Contradictedx402x402 Bazaar1 payer